Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11442
    Prev
    Next
    INDEX
    Explanations

    character representations or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manufacturers
    -0.07
    erchant
    -0.06
     merchants
    -0.06
     Manufacturers
    -0.06
    oser
    -0.06
    itesse
    -0.06
     manufactures
    -0.06
     quảng
    -0.06
    avar
    -0.06
     manufacturer
    -0.06
    POSITIVE LOGITS
     Remote
    0.12
     remote
    0.12
     Indigenous
    0.11
     remot
    0.10
    Remote
    0.10
     culturally
    0.10
    remote
    0.10
     Tribal
    0.09
    REMOTE
    0.09
     Cultural
    0.09
    Activations Density 0.001%

    No Known Activations